Server replication is an approach often used to improve service access efficiency and availability for a large number of clients. this paper adopts a simple service model and investigates a set of efficient algorithms...
详细信息
ISBN:
(纸本)0769521355
Server replication is an approach often used to improve service access efficiency and availability for a large number of clients. this paper adopts a simple service model and investigates a set of efficient algorithms for server selection in an anycast group under the condition of imprecise network delay. the algorithms use ticket-based probing approach to search the path with short delay and probe the server load at the same time and try to optimize the server and path delay at the same time. the simulation results demonstrate that our algorithms are efficient in terms of server response time for sever selection compared with several other server selection algorithms.
Traditionally, real-time requirements are expressed by means of deadlines, which are imposed by the environment on the system. this approach, however, is not well suited for expressing real-time requirements on the in...
详细信息
ISBN:
(纸本)076952124X
Traditionally, real-time requirements are expressed by means of deadlines, which are imposed by the environment on the system. this approach, however, is not well suited for expressing real-time requirements on the interaction between objects;such as found in distributed systems supporting autonomy of objects. this paper presents a coherent framework in which real-time requirements for such interacting objects can be expressed Two interrelated system layers are considered together: the communication layer and the distributed programming layer that describes how interactions between the objects are organized In particular, the paper evaluates the relationship between real-time requirements and real-time activities in distributed object-oriented systems.
the Function Block (FB) has been defined by the international Electro-technical Commission (IEC) as the basic construct for the development of reusable, interoperable, distributed control applications. Complete applic...
详细信息
ISBN:
(纸本)076952124X
the Function Block (FB) has been defined by the international Electro-technical Commission (IEC) as the basic construct for the development of reusable, interoperable, distributed control applications. Complete applications can be defined in the design level as networks of interconnected FBs. For these design models to be automatically converted to implementation ones, adopting the model integrated computing paradigm, an appropriate implementation meta-model should be defined. In this paper we describe two alternatives for the implementation of FB design models. the first one adopts the straight forward transformation of the FB design model to a high level language (C++, Java) implementation model. the second approach utilizes UML-RT models as an intermediate representation towards the final implementation model. Both approaches support the dynamic re-configuration of the control application and exploit our extensions to the IEC Execution Control Chart notation, to improve the expressiveness of the design model and the efficiency of the implementation one.
this paper describes an architecture for distributedcomputing on the RTLinux-GPL (GPL version of RTLinux, hereafter RTLinux) platform. the proposed architecture implements the CORBA (Common Object Request Broker Arch...
详细信息
ISBN:
(纸本)076952124X
this paper describes an architecture for distributedcomputing on the RTLinux-GPL (GPL version of RTLinux, hereafter RTLinux) platform. the proposed architecture implements the CORBA (Common Object Request Broker Architecture) model of computation, more specifically the minimum CORBA specification for embedded systems, and will also provide the extensions for real-time computing. Since RTLinux lacks networking capabilities, the architecture implements all the required functionality in a layered fashion: network drivers, TCP/IP stack and an ORB (Object Request Broker). Most of this work consists on a set of portings of some widely known Open Source Linux projects to RTLinux: Linux Ethernet device drivers, the lwIP (lightweight IP) TCP/IP stack and ORBit, which is a C language implementation of CORBA. this paper also describes some ORBit modifications that make ORBit to comply withthe Minimum CORBA specification.
the multigrid method adopted in conjunction withthe parallelcomputing is presented. the standard multigrid doubling the mesh size in all directions, called full-coarsening technique, suffers from the partitioning of...
详细信息
ISBN:
(纸本)076952138X
the multigrid method adopted in conjunction withthe parallelcomputing is presented. the standard multigrid doubling the mesh size in all directions, called full-coarsening technique, suffers from the partitioning of data for parallelcomputing. To remedy this problem, the semi-coarsening technique should be used instead. this paper is aimed to present an algorithm of the semi-coarsening multigrid technique combined withthe parallelcomputing technique. the parallelcomputing technique used is the one based on the distributed memory machine. the MPI library is adopted in order to exchange the data among processors. the solver code is developed for three-dimensional turbulent flows and validated withthe available experimental data.
Dependability of complex systems is a critical system-level issue, which is still insufficiently tackled today. We propose here the adoption of an aggressive model-driven development paradigm (AMDD) to adequately capt...
详细信息
ISBN:
(纸本)076952124X
Dependability of complex systems is a critical system-level issue, which is still insufficiently tackled today. We propose here the adoption of an aggressive model-driven development paradigm (AMDD) to adequately capture globally-scoped issues like interoperability and compatibility. AMDD moves most of the recurring problems of compatibility and consistency of a system's design, implementation and evolution from the coding and integration level to the modelling level. In particular it enables an economical treatment of cross-system issues. this approach has proven useful already for the design, realization and test of complex distributed applications. In this paper we discuss the potential and benefits of AMDD and present examples where it is already adopted.
For a long time embedded real-time systems have been designed as far as possible in a static manner. this means that they have been treated as pre-designed, off-line analysed, off-line mapped onto target systems, supp...
详细信息
ISBN:
(纸本)076952124X
For a long time embedded real-time systems have been designed as far as possible in a static manner. this means that they have been treated as pre-designed, off-line analysed, off-line mapped onto target systems, supported by customized but at run-time static real-time operating systems (RTOS), running on pre-assigned HW platforms. In this contribution some arguments for introducing more dynamics into real-time applications are given. Such dynamics finally may result in so called Autonomic Systems. When building autonomic real-time systems, specific support is needed. In this contribution some examples for such support are provided: Modelling techniques for distributed, self-modifying real-time systems, self modifying real-time operating systems, and usage self-modifying HW platforms.
Synchronous VLSI design is approaching a critical point, with clock distribution becoming an increasingly costly and complicated issue and power consumption rapidly emerging as a major concern. Hence, recently, there ...
详细信息
ISBN:
(纸本)0769521355
Synchronous VLSI design is approaching a critical point, with clock distribution becoming an increasingly costly and complicated issue and power consumption rapidly emerging as a major concern. Hence, recently, there has been a resurgence of interest in asynchronous digital design techniques as they promise to liberate VLSI systems from clock skew problems, offer the potential for low power and high performance and encourage a modular design philosophy which makes incremental technological migration a much easier task. In a pipelined architecture, if a control hazard occurs, the prefetched instructions following a hazard must be discarded and removed from the pipeline before instructions from the new stream are executed. In an asynchronous microprocessor the exact number of the prefetched instructions is nondeterministic and unpredictable. the processor must be able to distinguish between instructions originating from the branch or the exception target, which may thus be executed, and instructions already prefetched when the hazard took place, which must therefore be thrown away. this paper will discuss a distributed, asynchronous technique for dealing with control hazards in asynchronous pipelines where control hazards may potentially occur in more than one stage.
the paper presents an agent-based architecture facilitating implemetation of parallel evolutionary algorithms, utilising the novel concept of a flock. the model proposed is an extension to classical regional parallel ...
详细信息
ISBN:
(纸本)3540221239
the paper presents an agent-based architecture facilitating implemetation of parallel evolutionary algorithms, utilising the novel concept of a flock. the model proposed is an extension to classical regional parallel evolutionary algorithm. Flocks introduce additional level of organisation of the system, allowing for separation of distribution and evolution issues, and thus opening possibility of dynamic reconfiguration of subpopulations adequately to the structure of the problem being solved. Selected experimental results illustrate the idea "at work".
the paper describes the use of a wireless sensor network (WSN) for performing parallel pattern recognition computations. A complexity analysis indicates that the proposed algorithm is independent of the number of node...
详细信息
ISBN:
(纸本)076952138X
the paper describes the use of a wireless sensor network (WSN) for performing parallel pattern recognition computations. A complexity analysis indicates that the proposed algorithm is independent of the number of nodes and hence may scale up indefinitely withthe network. It's shown that any material object once overlaid with a WSN, develops a latent associative memory, which enables the object to memorise some of its critical internal states for a real time comparison withthose induced by the transient external conditions.
暂无评论